EPPS 6356 Data Visualization Project
This storyboard delivers our final project product by visualizing Formula 1 Racing data focused on analyzing information on the drivers and different circuits.
Multiple linear regression was utilized to determine which factors
are important to evaluate the best driver.
Wins = b0 + (Pole Wins) X1 + (Total Points) X2 + (Fastest Laps) X3 +
(Podiums) X4 + (1st WDC Age) X5 + e
Note: b0 is the intercept of the regression line and e is the model
error (residuals) or the variation in the model
R^2 = 0.9904, p-value = 5.769e-06
All factors were significant except Fastest Laps and Age. Tried to
evaluate the height factor, however, the p-value was truly not
significant since the p-value was 0.72785.
The residual values are not completely normally distributed. This
histogram is skewed a bit at the ends. In the normal Q-Q plot, the
normality appears to be more clear because the values follow a straight
line.
Different drivers’ race win records across various circuits are presented here. The legend on the bottom lists the circuits in the data set and then the bar chart visualizes the number of wins for each driver.
These 2 graphs are created using the “f1dataR” library!